Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    asking me about my

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ր
    0.42
    ร
    0.42
     otherworldly
    0.42
    連合
    0.40
    ห์
    0.39
    成像
    0.38
    次元
    0.38
    Factories
    0.38
    💚
    0.37
    ன்மை
    0.36
    POSITIVE LOGITS
     mujhe
    0.49
     бясплат
    0.48
    íveis
    0.47
     weekdays
    0.47
     জিজ্ঞেস
    0.46
     amplo
    0.45
     مجھے
    0.45
    ską
    0.45
     manually
    0.44
     advisable
    0.43
    Act Density 0.000%

    No Known Activations